检索结果-内蒙古大学图书馆

World Rehabilitation Robot Convention (WRRC)

作者： Jingjing Luo Shuo Wang Hongbo Wang Yuhui Cen Zhouhan Chen Yiheng Peng Xing Zhu Institute of AI and Robotics Academy for Engineering and Technology Fudan University Shanghai China Engineering Research Center of AI and Robotics Ministry of Education Shanghai China

ISBN: (数字)9798350355123

ISBN: (纸本)9798350355130

Photoplethysmography (PPG) is a non-invasive optical technique that provides valuable physiological information, including heart rate (HR), pulse wave (PW), and blood oxygen saturation (SpO2). However, wearable devices often have variable signal quality, lacking monitoring capabilities or precision in daily use. To address these limitations, we propose a multi-wavelength PPG-based patch physiological monitoring system. The system utilizes three PPG wavelengths of enhanced signal quality, leading to improved accuracy and potentially extracting a wider range of physiological information compared to standard devices. We evaluated the system's performance by extracting PPG signals from three locations on the human body and analyzing their quality. The results demonstrate that the system successfully extracts high-quality PW, enabling accurate estimation of HR, SpO2, and even blood pressure (BP). The BP estimation model, particularly with personalized adaptation, exhibits good performance. The system offers the potential for continuous, non-invasive measurement of a wider range of physiological parameters compared to traditional wearable devices, and its portability and ease of use make it a compelling solution for user-friendly daily healthcare monitoring.

关键词： Heart rate Performance evaluation Accuracy System performance Estimation Photoplethysmography Biomedical monitoring Wearable devices Monitoring Standards

来源：评论

学校读者我要写书评

暂无评论

Soft wearable flexible bioelectronics integrated with an anklefoot exoskeleton for estimation of metabolic costs and physical effort

引用

npj Flexible Electronics 2023年第1期7卷 535-544页

作者： Jihoon Kim Prakyath Kantharaju Hoon Yi Michael Jacobson Hyungkeun Jeong Hojoong Kim Jinwoo Lee Jared Matthews Nathan Zavanelli Hyeonseok Kim Heejin Jeong Myunghee Kim Woon-Hong Yeo IEN Center for Human-Centric Interfaces and Engineering and George W.Woodruff School of Mechanical Engineering Georgia Institute of TechnologyAtlantaGA 30332USA Department of Mechanical and Industrial Engineering the University of Illinois at ChicagoChicagoIL 60607USA Department of Mechanical Roboticsand Energy EngineeringDongguk UniversitySeoulRepublic of Korea Human Systems Engineering The Polytechnic SchoolIra A.Fulton Schools of EngineeringArizona State UniversityMesaAZ 85212USA Wallace H.Coulter Department of Biomedical Engineering Georgia Institute of Technology and Emory University School of MedicineAtlantaGA 30332USA Institute for Robotics and Intelligent Machines Parker H.Petit Institute for Bioengineering and BiosciencesInstitute for MaterialsNeural Engineering CenterGeorgia Institute of TechnologyAtlantaGA 30332USA

Activities and physical effort have been commonly estimated using a metabolic rate through indirect calorimetry to capture breath *** physical effort represents the work hardness used to optimize wearable robotic ***,personalization and rapid optimization of the effort are *** respirometry is the gold standard for estimating metabolic costs,this method requires a heavy,bulky,and rigid system,limiting the system’s field ***,this paper reports a soft,flexible bioelectronic system that integrates a wearable ankle-foot exoskeleton,used to estimate metabolic costs and physical effort,demonstrating the potential for real-time wearable robot adjustments based on *** from a set of activities,including walking,running,and squatting with the biopatch and exoskeleton,determines the relationship between metabolic costs and heart rate variability root mean square of successive differences(HRV-RMSSD)(R=−0.758).Collectively,the exoskeleton-integrated wearable system shows potential to develop a field-deployable exoskeleton platform that can measure wireless real-time physiological signals.

关键词： skeleton wear estimation

来源：评论

学校读者我要写书评

暂无评论

Optimal Adaptive Current Controller for Permanent Magnet Synchronous Motor with Performance Recovery Property 49

Optimal Adaptive Current Controller for Permanent Magnet Syn...

引用

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Chan Lee, Hyo Lim, Sun Jung, Il-Kyun Kim, Seok-Kyoon Graduate School of Creative Convergence Engineering Hanbat National University Daejeon Korea Republic of Intelligent Robotics Research Center of Korea Electronics Technology Institute Bucheon Korea Republic of Hanbat National University Department of Creative Convergence Engineering Daejeon Korea Republic of

ISBN: (纸本)9798350331820

This article exhibits a current controller guaranteeing the performance recovery property despite the parameter uncertainties for interior-mounted permanent magnet synchronous motors (IPMSMs). The contributions of the proposed method are as follows. The first one is to build the current control law for the closed-loop system to asymptotically recover the target current tracking performance, while estimating the unknown parameters. The second one is to present a systematic way assigning the optimal control gains by solving an optimization problem. The third one is to rigorously analyze the internal dynamics problem caused by the speed dynamics of IPMSMs. The efficacy of the proposed method is verified by conducting experiments where the proposed method is applied to a 5-kW IPMSM. © 2023 IEEE.

关键词： Closed loop systems

来源：评论

学校读者我要写书评

暂无评论

Topic Modeling Analysis of Chinese Medicine Literature on Potential Treatment

引用

Chinese Journal of Integrative Medicine 2024年第12期30卷 1128-1136页

作者： QIAN Jia-nan KANG Yan-lan HE You-cheng HU Hong-yi Department of Gastroenterology Longhua HospitalShanghai University of Traditional Chinese MedicineShanghai 200032China Institute of Digestive Diseases Longhua HospitalShanghai University of Traditional Chinese MedicineShanghai 200032China Institute of AI and Robotics Academy for Engineering&TechnologyFudan UniversityShanghai 200433China Clinical Research Center Longhua HospitalShanghai 200032China

Objective:To analyze Chinese medicine(CM)prescriptions for gastroesophageal reflux disease(GERD),we model topics on GERD-related classical CM literature,providing insights into the potential ***:Clinical guidelines were used to identify symptom terms for GERD,and CM literature from the database"Imedbooks"was retrieved for related prescriptions and their corresponding sources,indications,and other *** was applied to identify the main topics and visualize the ***:A total of 36,207entries are queried and 1,938 valid entries were acquired after manually *** topics were identified by BERTopic,including digestion function abate,stomach flu,respiratory-related symptoms,gastric dysfunction,regurgitation and gastrointestinal dysfunction in pediatric patients,vomiting,stroke and alcohol accumulation are associated with the risk of GERD,vomiting and its causes,regurgitation,epigastric pain,and symptoms of ***:Topic modeling provides an unbiased analysis of classical CM literature on GERD in a time-efficient and scale-efficient *** on this analysis,we present a range of treatment options for relieving symptoms,including herbal remedies and non-pharmacological interventions such as acupuncture and dietary therapy.

关键词： gastroesophageal reflux disease BERTopic prescription topic modeling Chinese medicine

来源：评论

学校读者我要写书评

暂无评论

A Novel Microdefect Imaging System for High-Reflective Material Surfaces

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： He, Zhiyong Lin, Song Xiao, Yafeng Fang, Hao Sun, Lining Soochow University School of Mechatronic Engineering Department of Automation Engineering Suzhou215000 China Soochow University Robotics and Microsystems Research Center Suzhou215000 China Institute of Robotics School of Mechatronic Engineering Harbin Institute of Technology Harbin150000 China

Highly reflective materials, owing to their reflective characteristics, pose challenges in imaging microdefects under conventional lighting, resulting in a substantial number of missed detections. This article presents an imaging method tailored for microdefects on the surfaces of such materials. An investigation into the imaging mechanisms of microdefects under varying illumination conditions is conducted, leading to the proposal of an edge-light scanning technique. Initially, this technique enhances the contrast of defect imaging optically, yielding a sequence of images with high-contrast defects. Subsequently, a contrast-weighted image synthesis algorithm is introduced to effectively mitigate the interference caused by bright and dark stripe backgrounds. Experimental evaluations of defect detection based on different algorithms demonstrate that the proposed imaging method is applicable to defects of various sizes and significantly improves the detection accuracy of microdefects. © 1963-2012 IEEE.

关键词： Imaging Surface morphology Optical surface waves Optical imaging Defect detection Feature extraction Lighting Image edge detection Steel Optical reflection

来源：评论

学校读者我要写书评

暂无评论

Advanced Structural Design for Humanoid Robot Upper Limbs

Advanced Structural Design for Humanoid Robot Upper Limbs

引用

robotics, Control and Automation (ICRCA), International Conference on

作者： Yifan Liu Hongwu Wang Dianzheng Wang Yunji Li Xiangkun Zhang Robotics Engineering Center The 21st Research Institute of CETC Shanghai China

ISBN: (数字)9798331544577

ISBN: (纸本)9798331544584

In this paper, the humanoid robot is taken as the object to study the influence of the design parameters of the dual-arm base on the workspace in the logistics handling scene. First, the humanoid robot and the handling target object are modeled, the influence of the dual-arm configuration and the base constraint conditions on the dual-arm workspace is quantitatively analyzed, the mathematical relationship between the variables is established, and the parameters of the dual-arm base are optimized to achieve the best workspace. Finally, the optimization effect is verified by experiments. The results show that the method can effectively improve the cooperative workspace of the two arms and provide ideas for the design of the base.

关键词： Automation Humanoid robots Arms Manipulators Stability analysis Mathematical models MATLAB Collision avoidance Optimization Logistics

来源：评论

学校读者我要写书评

暂无评论

SEMANTIC FLOW: LEARNING SEMANTIC FIELDS OF DYNAMIC SCENES FROM MONOCULAR VIDEOS 12

SEMANTIC FLOW: LEARNING SEMANTIC FIELDS OF DYNAMIC SCENES FR...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Tian, Fengrui Duan, Yueqi Wang, Angtian Guo, Jianfei Du, Shaoyi National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University China Tsinghua University China Johns Hopkins University United States Shanghai AI Laboratory China

In this work, we pioneer Semantic Flow, a neural semantic representation of dynamic scenes from monocular videos. In contrast to previous NeRF methods that reconstruct dynamic scenes from the colors and volume densities of individual points, Semantic Flow learns semantics from continuous flows that contain rich 3D motion information. As there is 2D-to-3D ambiguity problem in the viewing direction when extracting 3D flow features from 2D video frames, we consider the volume densities as opacity priors that describe the contributions of flow features to the semantics on the frames. More specifically, we first learn a flow network to predict flows in the dynamic scene, and propose a flow feature aggregation module to extract flow features from video frames. Then, we propose a flow attention module to extract motion information from flow features, which is followed by a semantic network to output semantic logits of flows. We integrate the logits with volume densities in the viewing direction to supervise the flow features with semantic labels on video frames. Experimental results show that our model is able to learn from multiple dynamic scenes and supports a series of new tasks such as instance-level scene editing, semantic completions, dynamic scene tracking and semantic adaption on novel scenes. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Research on Singular Avoidance Algorithm for Redundant Manipulators Based on Screw Theory

Research on Singular Avoidance Algorithm for Redundant Manip...

引用

robotics, Control and Automation (ICRCA), International Conference on

作者： Hongwu Wang Yifan Liu Lei Lv Yunji Li Xiangkun Zhang Robotics Engineering Center The 21st Research Institute of CETC Shanghai China

ISBN: (数字)9798331544577

ISBN: (纸本)9798331544584

The singularity avoidance problem of redundant DOF manipulator is studied in this paper. Firstly, a kinematic model of a 7-DOF manipulator was established based on the screw theory. Then, the singularity of the manipulator was analyzed, and the velocity level inverse kinematics algorithm for singularity avoidance was derived based on the minimum singular value as the singularity optimization index. Finally, a path planning experiment for singularity avoidance was conducted based on the velocity level inverse kinematics algorithm. The experimental results showed that the inverse kinematics algorithm has good accuracy, which verifies the effectiveness of the singularity avoidance algorithm and lays the foundation for the motion planning of redundant manipulators.

关键词： Redundancy Process control Kinematics Fasteners Manipulators Path planning Mathematical models Planning Indexes Optimization

来源：评论

学校读者我要写书评

暂无评论

Omni-dimensional dynamic convolution feature coordinate attention network for pneumonia classification

引用

Visual Computing for Industry,Biomedicine,and Art 2024年第1期7卷 196-208页

作者： Yufei Li Yufei Xin Xinni Li Yinrui Zhang Cheng Liu Zhengwen Cao Shaoyi Du Lin Wang School of Information Science and Technology Northwest UniversityXi’an 710127Shaanxi ProvinceChina Department of Ultrasound the Second Affiliated Hospital of Xi’an Jiaotong UniversityXi’anShaanxi Province 710004China National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applicationsand Institute of Artificial Intelligence and RoboticsXi’an Jiaotong UniversityXi’anShaanxi Province 710049China

Pneumonia is a serious disease that can be fatal,particularly among children and the *** accuracy of pneumonia diagnosis can be improved by combining artificial-intelligence technology with X-ray *** study proposes X-ODFCANet,which addresses the issues of low accuracy and excessive parameters in existing deep-learningbased pneumonia-classification *** network incorporates a feature coordination attention module and an omni-dimensional dynamic convolution(ODConv)module,leveraging the residual module for feature extraction from X-ray *** feature coordination attention module utilizes two one-dimensional feature encoding processes to aggregate feature information from different spatial ***,the ODConv module extracts and fuses feature information in four dimensions:the spatial dimension of the convolution kernel,input and output channel quantities,and convolution kernel *** experimental results demonstrate that the proposed method can effectively improve the accuracy of pneumonia classification,which is 3.77%higher than that of *** model parameters are 4.45M,which was reduced by approximately 2.5 *** code is available at https://***/limuni/X ODFCA NET.

关键词： Pneumonia Coordinate attention Dynamic convolution ResNet18 X-ODFCANet

来源：评论

学校读者我要写书评

暂无评论

Fuzzy-NMS: Improving 3D Object Detection With Fuzzy Classification in NMS

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-15页

作者： Wang, Li Zhang, Xinyu Zhao, Fachuan Wu, Chuze Wang, Yichen Song, Ziying Yang, Lei Xu, Bin Li, Jun Ge, Shuzhi Sam School of Machanical Engineering Beijing Institute of Technology Beijing China School of Vehicle and Mobility Tsinghua University Beijing China School of Computer and Information Technology Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing China Department of Electrical and Computer Engineering Interactive Digital Media Institute Social Robotics Laboratory National University of Singapore Singapore

Non-maximum suppression (NMS) is an essential post-processing module in many 3D object detection frameworks to remove overlapping candidate bounding boxes. However, an overreliance on classification scores and difficulties in determining appropriate thresholds can affect the resulting accuracy directly. To address these issues, we introduce fuzzy learning into NMS and propose a novel generalized Fuzzy-NMS module to achieve finer candidate bounding box filtering. The proposed Fuzzy-NMS module combines the volume and clustering density of candidate bounding boxes, refining them with a fuzzy classification method and optimizing the appropriate suppression thresholds to reduce uncertainty in the NMS process. Adequate validation experiments use the mainstream KITTI and large-scale Waymo 3D object detection benchmarks. The results of these tests demonstrate the proposed Fuzzy-NMS module can improve the accuracy of numerous recently NMS-based detectors significantly, including PointPillars, PV-RCNN, and IA-SSD, etc. This effect is particularly evident for small objects such as pedestrians and bicycles. As a plug-and-play module, Fuzzy-NMS does not need to be retrained and produces no obvious increases in inference time. IEEE

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：